An advanced Playwright-based web scraping skill with integrated anti-bot protection designed to bypass tough security measures like Cloudflare.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install coco-playwright-stealth-1-0-0
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install coco-playwright-stealth-1-0-0 using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Playwright Scraper Skill?
The Playwright Scraper Skill is a powerful addition to your collection of Openclaw Skills, engineered to handle the complexities of modern web scraping. By leveraging Playwright, this skill bridges the gap between basic text fetching and heavy-duty browser automation, allowing AI agents to seamlessly extract data from JavaScript-heavy environments and highly secure platforms.
What sets this skill apart is its specialized stealth capabilities. While traditional scrapers fail against modern anti-bot protections, this tool features dedicated scripts engineered to bypass Cloudflare and advanced detection mechanisms, yielding a 100% success rate on heavily protected community portals like Discuss.com.hk.
Playwright Scraper Skill Use Cases
- Extracting clean data from dynamic web applications that rely heavily on JavaScript rendering.
- Bypassing strict anti-bot mechanisms, challenge pages, and Cloudflare protection layers on high-security targets.
- Capturing structural page HTML and visual evidence via screenshots during the automated crawling process.
- Executing highly customized web scraping workflows tailored to mobile or desktop environments using custom environment variables.
How Playwright Scraper Skill Works
- Target Analysis: The user or AI agent evaluates the target URL and decides on the scraping approach based on the site's anti-bot level.
- Script Execution: The appropriate script (simple or stealth) is initiated via Node.js with optional environment variables for custom configurations.
- Anti-Bot Evasion: For protected sites, the stealth script injects specialized configurations before page load, hiding automation signatures and mimicking human navigation.
- Data Extraction: Playwright waits for the required DOM elements or network idle state to capture rendering results.
- Output Generation: The system returns a structured JSON payload containing the URL, title, content, execution metrics, and optional filesystem assets like screenshots.
Playwright Scraper Skill Setup
To get started with this skill, navigate to your skill directory and install the necessary dependencies including the Chromium browser binary:
cd playwright-scraper-skill
npm install
npx playwright install chromium
Playwright Scraper Skill Data Schema & Taxonomy
The skill structures execution outputs into clean JSON objects and optional asset files based on the chosen script.
JSON Output Schema
| Property | Type | Description |
|---|---|---|
url |
String | The final resolved URL that was scraped |
title |
String | The page title extracted from the HTML metadata |
content |
String | The text or HTML payload processed from the page context |
elapsedSeconds |
String | Execution duration tracking for performance auditing |
Generated Files
- Screenshots: PNG format images saved when using the stealth script (configurable via
SCREENSHOT_PATH). - HTML Source: Raw page markup captured post-rendering when
SAVE_HTML=trueis enabled.
Playwright Scraper Skill Advanced Features
- Automation Signature Masking: Explicitly overrides
navigator.webdriverto prevent detection from modern security scripts. - Human Behavior Emulation: Implements random operational delays and variable scrolling routines to accurately mimic natural user patterns.
- Device Profile Spoofing: Dynamically alters User-Agent strings to mimic authentic mobile (iPhone, Android) or desktop sessions.
- Environment Runtime Configuration: Fully configurable at runtime using variables for headful tracking (
HEADLESS=false), customized wait limits (WAIT_TIME), and asset outputs.
SKILL.md
Loading
Related Openclaw Skills
find-pr-agency
An AI agent skill that uses the ServiceGraph API to discover, shortlist, and enrich US-based public relations and communications agencies.
find-seo-agency
An AI agent skill to automatically find, filter, and enrich thousands of verified US SEO agencies using the ServiceGraph API.
Find Recruiting Firm
Find, shortlist, vet, and enrich US-based recruiting, executive search, RPO, and staffing firms using the ServiceGraph API.
Find Service Providers
A B2B research skill designed to query, filter, and enrich information on over 100,000 US professional service firms using the ServiceGraph API.
find-product-directories
An AI agent skill to find, filter, and rank over 1,000 product directories and SaaS launch sites for SEO backlinks and traffic.
Cron Hardening
A robust execution guide and configuration standard designed to secure resilient, error-free automated cron runs inside OpenClaw.
Featured*
